I recently started a new newsletter focus on AI education and already has over 50,000 subscribers. TheSequence is a no-BS( meaning no hype, no news etc) AI-focused newsletter that takes 5 minutes to read. The goal is to keep you up to date with machine learning projects, research papers and concepts. Most deep learning models we build these days are highly optimized for a specific type of dataset. Architectures that are good at processing textual data cant be applied to computer vision or audio analysis.

The work presented in this paper is to propose a reliable high-quality system of Convolutional Neural Network (CNN) for brain tumor segmentation with a low computation requirement. The system consists of a CNN for the main processing for the segmentation, a pre-CNN block for data reduction and post-CNN refinement block. The unique CNN consists of 7 convolution layers involving only 108 kernels and 20308 trainable parameters. It is custom-designed, following the proposed paradigm of ASCNN (application specific CNN), to perform mono-modality and cross-modality feature extraction, tumor localization and pixel classification. Each layer fits the task assigned to it, by means of (i) appropriate normalization applied to its input data, (ii) correct convolution modes for the assigned task, and (iii) suitable nonlinear transformation to optimize the convolution results. In this specific design context, the number of kernels in each of the 7 layers is made to be just-sufficient for its task, instead of exponentially growing over the layers, to increase information density and to reduce randomness in the processing. The proposed activation function Full-ReLU helps to halve the number of kernels in convolution layers of high-pass filtering without degrading processing quality. A large number of experiments with BRATS2018 dataset have been conducted to measure the processing quality and reproducibility of the proposed system. The results demonstrate that the system reproduces reliably almost the same output to the same input after retraining. The mean dice scores for enhancing tumor, whole tumor and tumor core are 77.2%, 89.2% and 76.3%, respectively. The simple structure and reliable high processing quality of the proposed system will facilitate its implementation and medical applications.

This paper proposes a novel split learning framework with multiple end-systems in order to realize privacypreserving deep neural network computation. In conventional split learning frameworks, deep neural network computation is separated into multiple computing systems for hiding entire network architectures. In our proposed framework, multiple computing end-systems are sharing one centralized server in split learning computation, where the multiple end-systems are with input and first hidden layers and the centralized server is with the other hidden layers and output layer. This framework, which is called as spatio-temporal split learning, is spatially separated for gathering data from multiple end-systems and also temporally separated due to the nature of split learning. Our performance evaluation verifies that our proposed framework shows nearoptimal accuracy while preserving data privacy.

Robots in our daily surroundings are increasing day by day. Their usability and acceptability largely depend on their explicit and implicit interaction capability with fellow human beings. As a result, social behavior is one of the most sought-after qualities that a robot can possess. However, there is no specific aspect and/or feature that defines socially acceptable behavior and it largely depends on the situation, application, and society. In this article, we investigate one such social behavior for collocated robots. Imagine a group of people is interacting with each other and we want to join the group. We as human beings do it in a socially acceptable manner, i.e., within the group, we do position ourselves in such a way that we can participate in the group activity without disturbing/obstructing anybody. To possess such a quality, first, a robot needs to determine the formation of the group and then determine a position for itself, which we humans do implicitly. The theory of f-formation can be utilized for this purpose. As the types of formations can be very diverse, detecting the social groups is not a trivial task. In this article, we provide a comprehensive survey of the existing work on social interaction and group detection using f-formation for robotics and other applications. We also put forward a novel holistic survey framework combining all the possible concerns and modules relevant to this problem. We define taxonomies based on methods, camera views, datasets, detection capabilities and scale, evaluation approaches, and application areas. We discuss certain open challenges and limitations in current literature along with possible future research directions based on this framework. In particular, we discuss the existing methods/techniques and their relative merits and demerits, applications, and provide a set of unsolved but relevant problems in this domain.

Recent advancements in deep learning, computer vision, and embodied AI have given rise to synthetic causal reasoning video datasets. These datasets facilitate the development of AI algorithms that can reason about physical interactions between objects. However, datasets thus far have primarily focused on elementary physical events such as rolling or falling. There is currently a scarcity of datasets that focus on the physical interactions that humans perform daily with objects in the real world. To address this scarcity, we introduce SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments. The SPACE simulator allows us to generate the SPACE dataset, a synthetic video dataset in a 3D environment, to systematically evaluate physics-based models on a range of physical causal reasoning tasks. Inspired by daily object interactions, the SPACE dataset comprises videos depicting three types of physical events: containment, stability and contact. These events make up the vast majority of the basic physical interactions between objects. We then further evaluate it with a state-of-the-art physics-based deep model and show that the SPACE dataset improves the learning of intuitive physics with an approach inspired by curriculum learning. Repository: https://github.com/jiafei1224/SPACE

Unsupervised domain adaptation (UDA) enables a learning machine to adapt from a labeled source domain to an unlabeled domain under the distribution shift. Thanks to the strong representation ability of deep neural networks, recent remarkable achievements in UDA resort to learning domain-invariant features. Intuitively, the hope is that a good feature representation, together with the hypothesis learned from the source domain, can generalize well to the target domain. However, the learning processes of domain-invariant features and source hypothesis inevitably involve domain-specific information that would degrade the generalizability of UDA models on the target domain. In this paper, motivated by the lottery ticket hypothesis that only partial parameters are essential for generalization, we find that only partial parameters are essential for learning domain-invariant information and generalizing well in UDA. Such parameters are termed transferable parameters. In contrast, the other parameters tend to fit domain-specific details and often fail to generalize, which we term as untransferable parameters. Driven by this insight, we propose Transferable Parameter Learning (TransPar) to reduce the side effect brought by domain-specific information in the learning process and thus enhance the memorization of domain-invariant information. Specifically, according to the distribution discrepancy degree, we divide all parameters into transferable and untransferable ones in each training iteration. We then perform separate updates rules for the two types of parameters. Extensive experiments on image classification and regression tasks (keypoint detection) show that TransPar outperforms prior arts by non-trivial margins. Moreover, experiments demonstrate that TransPar can be integrated into the most popular deep UDA networks and be easily extended to handle any data distribution shift scenarios.

Due to the sparsity and irregularity of the 3D data, approaches that directly process points have become popular. Among all point-based models, Transformer-based models have achieved state-of-the-art performance by fully preserving point interrelation. However, most of them spend high percentage of total time on sparse data accessing (e.g., Farthest Point Sampling (FPS) and neighbor points query), which becomes the computation burden. Therefore, we present a novel 3D Transformer, called Point-Voxel Transformer (PVT) that leverages self-attention computation in points to gather global context features, while performing multi-head self-attention (MSA) computation in voxels to capture local information and reduce the irregular data access. Additionally, to further reduce the cost of MSA computation, we design a cyclic shifted boxing scheme which brings greater efficiency by limiting the MSA computation to non-overlapping local boxes while also preserving cross-box connection. Our method fully exploits the potentials of Transformer architecture, paving the road to efficient and accurate recognition results. Evaluated on classification and segmentation benchmarks, our PVT not only achieves strong accuracy but outperforms previous state-of-the-art Transformer-based models with 9x measured speedup on average. For 3D object detection task, we replace the primitives in Frustrum PointNet with PVT layer and achieve the improvement of 8.6%.

Quantization is a technique for reducing deep neural networks (DNNs) training and inference times, which is crucial for training in resource constrained environments or time critical inference applications. State-of-the-art (SOTA) approaches focus on post-training quantization, i.e. quantization of pre-trained DNNs for speeding up inference. Little work on quantized training exists and usually, existing approaches re-quire full precision refinement afterwards or enforce a global word length across the whole DNN. This leads to suboptimal bitwidth-to-layers assignments and re-source usage. Recognizing these limits, we introduce ADEPT, a new quantized sparsifying training strategy using information theory-based intra-epoch precision switching to find on a per-layer basis the lowest precision that causes no quantization-induced information loss while keeping precision high enough for future learning steps to not suffer from vanishing gradients, producing a fully quantized DNN. Based on a bitwidth-weighted MAdds performance model, our approach achieves an average speedup of 1.26 and model size reduction of 0.53 compared to standard training in float32 with an average accuracy increase of 0.98% on AlexNet/ResNet on CIFAR10/100.

Imagine if researchers could use 8K premium resolution imaging techniques as seen on premium TVs to scan electron microscopy which is an essential equipment for material research. According to ScienceDaily, a new joint research time from both the Korea Institute of Materials Science, or KIMS, and POSTECH have applied deep learning in order to scan electron microscopy or SEM. This was in order to develop a super-resolution imaging technique which can help convert low-resolution electron backscattering diffraction, or EBSD, microstructure images that were obtained from other conventional analysis equipment into higher super-resolution images. The study findings were officially published in the npj Computational Materials. When it comes to modern-day materials research, SEM images actually play a huge role in developing new materials starting from microstructure visualization and characterization, as well as in the whole numerical material behavior analysis. AI has previously been used for a series of other health functions like AI being able to detect early stages of dementia.

Researchers in the UK have developed a machine learning biometric system capable of identifying individuals from the shape of their hands. The intent of the work is to aide in identifying offenders, particularly in cases of sexual offenders that have recorded their crimes, where hand information is often the only biometric signal available. The paper, entitled Hand-based Person Identification Using Global and Part-aware Deep Feature Representation Learning, and proposes a new ML framework called Global and Part-Aware Network (GPA-Net). In GPA-Net, two distinct 3D tensors (global and local) are obtained by passing the source image through stacked convolutional layers on the ResNet50 backbone network. Each of the analytical avenues will make an identity prediction.